Update README.md

README.md

@@ -20,3 +20,24 @@ language:
 This mistral model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
 
 [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
+
+Info:
+I trained these Models on Google Colab with a Dataset i created out of the official CPE-Dictionary.
+The Dataset is formatted in the Alpaca Format:
+
+alpaca_prompt = """Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.
+
+### Instruction:
+{}
+
+### Input:
+{}
+
+### Response:
+{}"""
+
+For the best results with this Model use this format when interacting with the model:
+
+prompt = alpaca_prompt.format(f"What is the CPE for {vendor} {productname}. Only return the CPE", "", "")
+
+this is the exact wording i used i the dataset. Input and Response should be left blank.